Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1946 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.6527. Min Act: -0.1700

Data Index: 8677068 (Open Web Text)

Max Activating Token Index: 407

Text #1

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.5335. Min Act: -0.1700

Data Index: 8505036 (Open Web Text)

Max Activating Token Index: 431

Text #2

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.5144. Min Act: -0.1700

Data Index: 7619798 (Open Web Text)

Max Activating Token Index: 219

Text #3

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4950. Min Act: -0.1700

Data Index: 4124415 (Open Web Text)

Max Activating Token Index: 950

Text #4

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.5172. Min Act: -0.1700

Data Index: 4250352 (Open Web Text)

Max Activating Token Index: 36

Text #5

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.5065. Min Act: -0.1700

Data Index: 1908654 (Open Web Text)

Max Activating Token Index: 1017

Text #6

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.5175. Min Act: -0.1700

Data Index: 1055447 (Open Web Text)

Max Activating Token Index: 458

Text #7

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4826. Min Act: -0.1700

Data Index: 6217159 (Open Web Text)

Max Activating Token Index: 391

Text #8

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.5175. Min Act: -0.1700

Data Index: 1512823 (Open Web Text)

Max Activating Token Index: 146

Text #9

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4839. Min Act: -0.1700

Data Index: 2439573 (Open Web Text)

Max Activating Token Index: 509

Text #10

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4793. Min Act: -0.1700

Data Index: 3862462 (Open Web Text)

Max Activating Token Index: 732

Text #11

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4823. Min Act: -0.1700

Data Index: 6464488 (Open Web Text)

Max Activating Token Index: 710

Text #12

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4905. Min Act: -0.1700

Data Index: 375712 (Open Web Text)

Max Activating Token Index: 606

Text #13

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4621. Min Act: -0.1700

Data Index: 2144461 (Open Web Text)

Max Activating Token Index: 890

Text #14

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4415. Min Act: -0.1700

Data Index: 8670813 (Open Web Text)

Max Activating Token Index: 472

Text #15

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4651. Min Act: -0.1700

Data Index: 1322843 (Open Web Text)

Max Activating Token Index: 854

Text #16

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4405. Min Act: -0.1700

Data Index: 5849160 (Open Web Text)

Max Activating Token Index: 711

Text #17

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4477. Min Act: -0.1700

Data Index: 5945589 (Open Web Text)

Max Activating Token Index: 572

Text #18

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4545. Min Act: -0.1700

Data Index: 699234 (Open Web Text)

Max Activating Token Index: 461

Text #19

Max Range: 3.6527. Min Range: -3.6527

Max Act: 3.4397. Min Act: -0.1700

Data Index: 2483033 (Open Web Text)

Max Activating Token Index: 381